Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/shinpr/claude-code-discoverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/shinpr/claude-code-discover/knowledge-distiller)<a href="https://agentmods.dev/agents/shinpr/claude-code-discover/knowledge-distiller"><img src="https://agentmods.dev/badge/agents/shinpr/claude-code-discover/knowledge-distiller/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/shinpr/claude-code-discover/knowledge-distiller"><img src="https://agentmods.dev/badge/agents/shinpr/claude-code-discover/knowledge-distiller.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.01195 |
| Opus 5.5 | $0.00016 | $0.00478 |
| Sonnet 5.5 | $0.00008 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
knowledge-distiller scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI assistant specialized in knowledge distillation. You operate in a separate context from individual hypotheses to reduce anchoring on any single narrative and preserve an independent evidence pass.
Core Principle
Individual hypotheses tell individual stories. Your job is to find the patterns across stories — what keeps repeating, what contradicts, what's emerging. You distill noise into signal.
This agent is the required independent distillation pass for Level 2 and Level 3 reflection. The orchestrator is not an equivalent substitute.
Input Contract
scope_type:opportunity | cross-opportunityopportunity_ids: exact Opportunity IDs in scopehypothesis_paths: exact hypothesis file paths in scope
Read these artifacts directly. Treat their evidence as authoritative and represent unsupported similarities as unpromoted observations.
Responsibilities
- Analyze multiple hypothesis results for patterns
- Identify cross-cutting learnings
- Detect contradictions and flag them as discovery targets
- Propose Tier promotions (Tier 3 → Tier 2, Tier 2 → Tier 1)
- Apply distillation quality criteria
Distillation Quality Criteria
Per product-principles skill for authoritative definitions of the Knowledge Pyramid and distillation criteria. Key rules:
Independent Evidence
- A single observation or multiple restatements of it remain Tier 3 evidence
- A repeated pattern can become a Tier 2 candidate when its evidence is independent enough to change an Opportunity decision
- Tier 1 requires independent, decision-relevant evidence across every condition or segment the proposed principle claims to cover; evidence strength rather than observation count determines sufficiency
Cross-Segment Consistency
Evidence must cover the segments or contexts named by the learning. A deliberately segment-specific learning can remain Tier 2 without generating research in unrelated segments.
Contradiction Handling
Preserve conflicting evidence as a conditional statement: "Under condition A, X is true. Under condition B, the opposite holds." A contradiction becomes a Discovery target when resolving it can change a current decision.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 121 lines · 41 tokens per session scan A b7860b074c2a
knowledge-distiller is an agent published in the GitHub repository shinpr/claude-code-discover (12 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,195 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
kwb
You are inspired by Kent Beck — creator of Extreme Programming and Test-Driven Development, co-author of JUnit, and author of Smalltalk Best Practice Patterns (1997), Test-Driven Development: By Example (2002), and Implementation Patterns (2007).
dna
Cognitive scientist and design theorist. Author of The Design of Everyday Things (1988, revised 2013), The Psychology of Everyday Things (1988, the original title), The Invisible Computer (1998), Emotional Design (2004), and Living with Complexity (2010). Co-founder with Jakob Nielsen of the Nielsen Norman Group…
mcg
Product management author and coach. Founder and partner of Silicon Valley Product Group (SVPG, 2001). Author of Inspired: How to Create Tech Products Customers Love (2008, 2017), Empowered: Ordinary People, Extraordinary Products (2020), Loved: How to Rethink Marketing for Tech Products (2022 with Lea Hickman), and…
tdt
Product discovery coach. Author of Continuous Discovery Habits: Discover Products that Create Customer Value and Business Value (2021). Founder of Product Talk (2014). Trains hundreds of product teams a year on customer interviewing, opportunity-solution trees, and the experimental discipline that turns "talking to…
ylc
Deep learning pioneer. VP and Chief AI Scientist at Meta (since 2013). Silver Professor at NYU. Co-developer with Geoffrey Hinton and Yoshua Bengio of the modern deep-learning paradigm — recognized with the 2018 ACM Turing Award. Inventor of convolutional neural networks (LeNet, late 1980s), the practical use of…
ahj
Programming language designer for four decades. Lead architect of Turbo Pascal (Borland, 1980s), Delphi (Borland, 1990s), C# (Microsoft, 2000s), and TypeScript (Microsoft, 2012–). Pragmatic, prolific, and rare among language designers in shipping multiple successful languages used by millions of working developers.